detect("Hello world") say nl!

[cseshahriar]

from langdetect import detect
detect("Hello world")
'nl'

[pouria-ariafar]

I have the same problem.
from langdetect import detect_langs
detect_langs("Buy iPhone")
[vi:0.9999983729464899]

This problem exists in most words.!!

[pouria-ariafar]

@cseshahriar
I suggest you use the lingua library, it is much more accurate.
I tested and was satisfied.
https://github.com/pemistahl/lingua-py

[vsmelov]

import pprint
from langdetect import detect_langs

langdetect_ranks = detect_langs("Hello")
pprint.pprint(langdetect_ranks)

[no:0.6405345342314349, fi:0.3594654657685652]

[huelsgp27]

Interesting

[dwvisser]

From this project's README:

Language detection algorithm is non-deterministic, which means that if you try to run it on a text which is either too short or too ambiguous, you might get different results everytime you run it.